Balázs Kiss

A hundred ways to wreck your AI - the (in)security of machine learning systems

Loading a pre-trained model can lead to remote code execution. Learn how the `pickle` format creates a massive security hole in your AI supply chain.

A hundred ways to wreck your AI - the (in)security of machine learning systems
#1about 4 minutes

The security risks of AI-generated code

AI systems can generate code quickly but may introduce vulnerabilities or rely on outdated practices, highlighting that all AI systems are fundamentally code and can be exploited.

#2about 5 minutes

Fundamental AI vulnerabilities and malicious misuse

AI systems are prone to classic failures like overfitting and can be maliciously manipulated through deepfakes, chatbot poisoning, and adversarial patterns.

#3about 1 minute

Exploring threat modeling frameworks for AI security

Several organizations like OWASP, NIST, and MITRE provide threat models and standards to help developers understand and mitigate AI security risks.

#4about 6 minutes

Deconstructing AI attacks from evasion to model stealing

Attack trees categorize novel threats like evasion with adversarial samples, data poisoning to create backdoors, and model stealing to replicate proprietary systems.

#5about 2 minutes

Demonstrating an adversarial attack on digit recognition

A live demonstration shows how pre-generated adversarial samples can trick a digit recognition model into misclassifying numbers as zero.

#6about 5 minutes

Analyzing supply chain and framework security risks

Security risks extend beyond the model to the supply chain, including backdoors in pre-trained models, insecure serialization formats like Pickle, and vulnerabilities in ML frameworks.

#7about 1 minute

Choosing secure alternatives to the Pickle model format

The HDF5 format is recommended as a safer, industry-standard alternative to Python's insecure Pickle format for serializing machine learning models.

Related jobs
Jobs that call for the skills explored in this talk.

Matching moments

The dual nature of machine learning's power
03:07 MIN

The dual nature of machine learning's power

Machine Learning: Promising, but Perilous

Understanding the current state of AI security challenges
00:04 MIN

Understanding the current state of AI security challenges

Delay the AI Overlords: How OAuth and OpenFGA Can Keep Your AI Agents from Going Rogue

The ethical risks of outdated and insecure AI models
13:54 MIN

The ethical risks of outdated and insecure AI models

AI & Ethics

Understanding the security risks of AI-generated code
17:12 MIN

Understanding the security risks of AI-generated code

Exploring AI: Opportunities and Risks in Development

Understanding the security risks of AI-generated code
09:25 MIN

Understanding the security risks of AI-generated code

WeAreDevelopers LIVE – Building on Algorand: Real Projects and Developer Tools

Managing security risks of AI-assisted code generation
08:03 MIN

Managing security risks of AI-assisted code generation

WWC24 - Chris Wysopal, Helmut Reisinger and Johannes Steger - Fighting Digital Threats in the Age of AI

How AI coding assistants impact developer skills
19:57 MIN

How AI coding assistants impact developer skills

Navigating the Future of Junior Developers in Tech

AI privacy concerns and prompt engineering
25:33 MIN

AI privacy concerns and prompt engineering

Coffee with Developers - Cassidy Williams -

Featured Partners

Related Videos

See all videos
Hacking AI - how attackers impose their will on AI27:02

Hacking AI - how attackers impose their will on AI

Mirko Ross

Machine Learning: Promising, but Perilous27:19

Machine Learning: Promising, but Perilous

Nura Kawa

The AI Security Survival Guide: Practical Advice for Stressed-Out Developers30:36

The AI Security Survival Guide: Practical Advice for Stressed-Out Developers

Mackenzie Jackson

Skynet wants your Passwords! The Role of AI in Automating Social Engineering31:19

Skynet wants your Passwords! The Role of AI in Automating Social Engineering

Wolfgang Ettlinger & Alexander Hurbean

Beyond the Hype: Building Trustworthy and Reliable LLM Applications with Guardrails29:00

Beyond the Hype: Building Trustworthy and Reliable LLM Applications with Guardrails

Alex Soto

GenAI Security: Navigating the Unseen Iceberg24:33

GenAI Security: Navigating the Unseen Iceberg

Maish Saidel-Keesing

Staying Safe in the AI Future27:26

Staying Safe in the AI Future

Cassie Kozyrkov

Prompt Injection, Poisoning & More: The Dark Side of LLMs23:24

Prompt Injection, Poisoning & More: The Dark Side of LLMs

Keno Dreßel

From learning to earning

Jobs that call for the skills explored in this talk.